agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes commands and examples that embed plaintext secrets verbatim (e.g., fill "password123", --headers '{"Authorization":"Bearer "}', set credentials user pass, cookies/storage retrieval), which would require the LLM to output secret values directly.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). This skill explicitly navigates to arbitrary external URLs via commands like "agent-browser open " and then snapshots and reads page content (e.g., "agent-browser snapshot -i", "agent-browser get text @e1"), meaning it fetches and interprets untrusted third-party webpages which can materially influence subsequent interactions.